39
 40
 41def _download_file(item):
 42    """ Helper function to pass (url, target) to ``download_file``. """ 43    return download_file(item[0], item[1])
 44
 45

264        return self.parse_tokens(tokens)
265
266    def parse_tokens(self, tokens):
267        """ Get segments from sequence of tokens. """268        valid_tokens = self.get_valid_tokens(tokens)
269
270        if len(valid_tokens) <= 0:

169        return audio_files
170
171    def get_reader_info(self, article_path):
172        """ Return info about the reader of the article. """173
174        meta_path = os.path.join(article_path, 'audiometa.txt')
175        with open(meta_path, 'r', encoding='utf-8') as f:

124        return audiomate.Corpus.from_corpus(corpus)
125
126    def get_articles(self, path):
127        """ Return the list of article-paths """128        article_paths = []
129
130        for dirname in os.listdir(path):

 49
 50
 51class SWCReader(base.CorpusReader):
 52    """ Reader for the Spoken Wikipedia Corpus. """ 53
 54    @classmethod
 55    def type(cls):